Skills for Real Engineers. Straight from my .agents directory.
auto-research
Agent skill fromhuytieu/COG-second-brain
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
How to install auto-research
npx skills add huytieu/COG-second-brain# or add only this skill to Claude Code: copy the folder
skills/auto-research/
# into
~/.claude/skills/auto-research/ (all projects)
.claude/skills/auto-research/ (one project)
1# COG Auto Research Skill23## When to Invoke4- User asks a strategic question requiring deep research5- User says "research", "auto-research", "investigate", "strategic analysis", "deep dive into [topic]"6- User wants to understand market forces, competitive dynamics, technology trajectories, or strategic options7- User needs evidence-based analysis with real sources to support decision-making89Inspired by Karpathy's autoresearch — but for strategic thinking instead of ML training.1011## Agent Mode Awareness1213**Check `agent_mode` in `00-inbox/MY-PROFILE.md` frontmatter:**14- If `agent_mode: team` — use the full parallel agent execution strategy (5-7 agents). This skill benefits massively from team mode.15- If `agent_mode: solo` — run 2-3 sequential research passes with WebSearch/WebFetch, produce a lighter analysis without the full multi-thread structure.1617## Command: `/auto-research`1819## Input20The user provides a strategic question or topic as the command argument. Examples:21- "If foundation models commoditize, what happens to LLM wrapper companies?"22- "Future of the testing industry as AI capabilities expand"23- "Should we build vs buy vs partner for our AI layer?"24- "What are the strategic options for Scout if OpenAI launches a testing product?"2526---2728## Execution Strategy2930### Phase 1: Question Decomposition (Orchestrator — 2 minutes)3132Break the user's strategic question into 5-7 **research threads** that together will provide a comprehensive answer. Each thread should be:33…
Excerpt shown under the repository's MIT license.
More skills in COG-second-brain
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
